- Simple naive versions built with numpy - source
- Basic Tensorflow version - source
- Convolutional neural net - source
- Transfer learning with Tensorflow MobileNet - source
- Utils to create data pipelines and to use saved tensorflow models
Model Architecture: Transfer learning with Tensorflow.MobileNetV3Large
neural net.
Dataset: Stanford Dogs Dataset
The most accurate model achieved 77% validation accuracy:
- Model source
- Google colab
- Model is deployed via the Telegram Bot
- http://vision.stanford.edu/aditya86/ImageNetDogs/
- https://www.kaggle.com/datasets/prasunroy/natural-images
- https://www.kaggle.com/datasets/jessicali9530/stanford-dogs-dataset
Inspired by: https://www.coursera.org/specializations/deep-learning
Run pip install -e .
in the ROOT folder for the local development